{"id":168704,"date":"2015-11-01T00:00:00","date_gmt":"2015-11-01T00:00:00","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/msr-research-item\/traffic-prediction-in-a-bike-sharing-system\/"},"modified":"2018-10-16T20:47:34","modified_gmt":"2018-10-17T03:47:34","slug":"traffic-prediction-in-a-bike-sharing-system","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/traffic-prediction-in-a-bike-sharing-system\/","title":{"rendered":"Traffic Prediction in a Bike-Sharing System"},"content":{"rendered":"<div class=\"asset-content\">\n<p>Bike-sharing systems are widely deployed in many major cities, providing a conven\u00adient tra\u00adn\u00ads\u00ad\u00adpor\u00adtation mode for citizens\u2019 comm\u00adutes. As the rents\/returns of bikes at different stations during different periods are unbalanced, the bikes in a system need to be rebalanced all the time. Real-time monitoring cannot tackle this problem well as it is too late to reallocate bikes after an unbalance has occurred. In this paper, we propose a hierarchical prediction model to predict the check-out\/in of each station cluster in a future period so that reallocation can be executed in advance. We propose a bipartite clustering algorithm to cluster stations into groups, based on which the hierarchical prediction of check-out\/in can be done. After the entire traffic of the whole city is obtained by a Gradient Boosting Regression Tree (GBRT), a multi-similarity-based infer\u00aden\u00adce model is proposed to predict the check-out propor\u00adtion across clusters and the inter-cluster transition matrix. Thus, the check-out across clusters can be calculated easily. Then, each cluster\u2019s check-in is inferred from the check-out, inter-cluster transition and trip duration. We evaluate our models on two bike-sharing systems in New York (NY) and Washington (WA), respectively, to confirm our models\u2019 advanta\u00adges beyond baseline approaches.<\/p>\n<\/div>\n<p>(<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2016\/02\/Codes.zip\">Code<\/a>)(<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2016\/02\/Data.zip\">Data<\/a>)(<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2015\/11\/traffic-prediction-in-a-bike-sharing-system-yuzheng.pptx\">PPT<\/a>)<\/p>\n<p><span id=\"9e5fb397-3fe9-4bfc-b7bb-c1233e73ce24\" class=\"ImageBlock fn\"><img decoding=\"async\" id=\"Image9e5fb397-3fe9-4bfc-b7bb-c1233e73ce24\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2016\/03\/\/urbancomputing-flyer-bike.png\" alt=\"\" \/><span id=\"ImageCaption9e5fb397-3fe9-4bfc-b7bb-c1233e73ce24\" class=\"ImageCaptionCoreCss ImageCaption\"><\/span><\/span><\/p>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Bike-sharing systems are widely deployed in many major cities, providing a conven\u00adient tra\u00adn\u00ads\u00ad\u00adpor\u00adtation mode for citizens\u2019 comm\u00adutes. As the rents\/returns of bikes at different stations during different periods are unbalanced, the bikes in a system need to be rebalanced all the time. Real-time monitoring cannot tackle this problem well as it is too late to [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13556,13563],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-168704","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-data-platform-analytics","msr-locale-en_us"],"msr_publishername":"ACM SIGSPATIAL 2015","msr_edition":"Proceedings of the 23rd ACM International Conference on Advances in Geographical Information Systems","msr_affiliation":"","msr_published_date":"2015-11-01","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"204128","msr_publicationurl":"","msr_doi":"10.1145\/2820783.2820837","msr_publication_uploader":[{"type":"file","title":"traffic%20prediction%20in%20a%20bike%20sharing%20system.pdf","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/traffic20prediction20in20a20bike20sharing20system.pdf","id":204128,"label_id":0},{"type":"file","title":"traffic prediction in a bike-sharing system-yuzheng","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2015\/11\/traffic-prediction-in-a-bike-sharing-system-yuzheng.pptx","id":247070,"label_id":0},{"type":"file","title":"Codes.zip","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/Codes.zip","id":204130,"label_id":0},{"type":"file","title":"Data.zip","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/Data.zip","id":204129,"label_id":0},{"type":"doi","title":"10.1145\/2820783.2820837","viewUrl":false,"id":false,"label_id":0}],"msr_related_uploader":"","msr_attachments":[{"id":247070,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2015\/11\/traffic-prediction-in-a-bike-sharing-system-yuzheng.pptx"},{"id":204130,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/Codes.zip"},{"id":204129,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/Data.zip"},{"id":204128,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/traffic20prediction20in20a20bike20sharing20system.pdf"}],"msr-author-ordering":[{"type":"text","value":"Yexin Li","user_id":0,"rest_url":false},{"type":"user_nicename","value":"yuzheng","user_id":35088,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=yuzheng"},{"type":"text","value":"Huichu Zhang","user_id":0,"rest_url":false},{"type":"text","value":"Lei Chen","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[199560],"msr_event":[],"msr_group":[],"msr_project":[170824],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/168704"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":3,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/168704\/revisions"}],"predecessor-version":[{"id":530392,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/168704\/revisions\/530392"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=168704"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=168704"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=168704"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=168704"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=168704"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=168704"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=168704"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=168704"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=168704"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=168704"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=168704"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=168704"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=168704"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=168704"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=168704"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}